
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Junyeol Blog</title>
      <link>https://junyeol.blog/blog</link>
      <description>Read, build, leave a trail.</description>
      <language>ko-KR</language>
      <managingEditor>junyeolkim00@gmail.com (junyeol kim)</managingEditor>
      <webMaster>junyeolkim00@gmail.com (junyeol kim)</webMaster>
      <lastBuildDate>Tue, 11 Aug 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://junyeol.blog/tags/리랭킹/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://junyeol.blog/blog/tech/rag-hybrid-search-reranking</guid>
    <title>RAG 개념 정리 (2) — 검색 정확도 올리기: 하이브리드 서치, 리랭킹, 쿼리 재작성</title>
    <link>https://junyeol.blog/blog/tech/rag-hybrid-search-reranking</link>
    <description>벡터 검색만으로는 왜 부족한지, BM25와의 하이브리드 서치·크로스인코더 리랭킹·쿼리 재작성으로 검색 정확도를 올리는 방법을 실전 수치와 함께 정리</description>
    <pubDate>Tue, 11 Aug 2026 00:00:00 GMT</pubDate>
    <author>junyeolkim00@gmail.com (junyeol kim)</author>
    <category>RAG</category><category>하이브리드서치</category><category>리랭킹</category><category>쿼리재작성</category><category>챗봇</category>
  </item>

    </channel>
  </rss>
